Computer Vision and Artificial Intelligence

Gang Hua

Gang Hua, Ph.D.

Principal Researcher/Research Manatger

Microsoft Research Asia

firstnamelastname AT gmail.com 

[Home][Research][Publications][Services][Collaboration]

[Vision Lab][Teaching] @Stevens Institute of Technology


Selected Research Work Grouped by Topics



Human Centered Visual Computing

 

Integration of Human and Machine Intelligence

Collaborative Active Learning

Collaborative Active Visual Recognition from the Crowds:

  • Gang Hua, Chengjiang Long^, Ming Yang, and Yan Gao, "Collaborative Active Learning of a Kernel Machine Ensemble for Recognition", in Proc. IEEE International Conf. on Computer Vision (ICCV'2013), Sydney, Australia, December, 2013.
  • Chengjiang Long^, Gang Hua, and Ashish Kapoor, "Active Visual Recognition with Expertise Estimation in Crowdsourcing", in Proc. IEEE International Conf. on Computer Vision (ICCV'2013), Sydney, Australia, December, 2013.  
ContextModel

Contextual Models for Interactive Visual Recognition:

 

Human Sensing from Unconstrained Images and Videos

PEP Model
Elastic Partial Matching

Probabilistic Elastic Part Model for Face Recognition:

  • Haoxiang Li^, Gang Hua, Zhe Lin, Jonathan Brandt, and Jianchao Yang, "Probabilistic Elastic Matching for Pose Variant Face Verification", in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR'2013), Portland, OR, June 2013.
  • Haoxiang Li^, Gang Hua, Zhe Lin, Jonathan Brandt, and Jianchao Yang, "Probabilistic Elastic Part Model for Unsupervised Face Detector Adaptation", in Proc. IEEE International Conf. on Computer Vision (ICCV'2013), Sydney, Australia, December, 2013.

Elastic Matching for Face Recognition:

Motion

Visual Human Motion Analysis:

Detection

Human Detection:

 

Vision based Interaction

Vision based Interaction

Big Visual Data Analytics:

 

 Low Level Image Feature and Descriptors

Local Descriptor

Learning Compact Local Image Descriptors:

Effecient Feature Detection:

 

Visual Data Mining

Object Discovery

Weakly Supervised Object Discovery and Recognition:

 

Webscale Unconstrained Video Event Recognition

Video Event Recognition

Semantic Attribute based Representation:

  • Michele Merler*, Bert Huang, Lexing Xie, Gang Hua, and Apostol Natsev, "Semantic Model Vectors for Complex Video Event Recognition", IEEE Trans. on Multimedia, Vol. 14, Issue 1, pp.88-101, February, 2012 .
  • Noel C. F. Codella, Gang Hua, Liangliang Cao, Michele Merler, Leiguang Gong, Matthew Hill, and John R. Smith, "Large-Scale Video Event Classification using Dynamic Pyramid Matching of Visual Semantics,'' in Proc. IEEE International Conf. on Image Processing (ICIP'2013) , Melbourne, Australia, September, 2013.
  • Liangliang Cao, Yadong Mu, Apostol Natsev, Shih-Fu Chang, Gang Hua, and John R. Smith, "Scene Aligned Pooling for Complex Video Recognition", in Proc. European Conf. on Computer Vision (ECCV'2012), Firenze, Italy, October, 2012.
  • Noel C. F. Codella, Apostol Natsev, Gang Hua, Matthew Hill, Liangliang Cao, Leiguang Gong, and John R. Smith, "Video Event Detection using Temporal Pyramids of Visual Semantics with Kernel Optimization and Model Subspace Boosting", in Proc. IEEE International Conference on Multimedia and Expo (ICME'2012) , Melbourne, Australia, July, 2012. (Oral Presentation)
  • Liangliang Cao, Shih-Fu Chang, Noel Codella, Courtenay Cotton, Dan Ellis, Leiguang Gong, Matthew Hill, Gang Hua, John Kender, Michele Merler, Yadong Mu, Apostol Natseve, John R. Smith, "IBM Research and Columbia University TRECVID-2011 Multimedia Event Detection (MED) System," NIST TRECVID Workshop, 2011.
 

Webscale Image Search

Internet Image Search

Contextual and Semantic Representation:


Visual Tracking

 

 Robust Tracking

Robust Tracking

Adaptive Observation Model:

 

Multiple Complex Motion Analysis

Contextual Motion Analysis

Contextual Multiple Motion Analysis:

Deformation

Complex Deformable Motion Analysis:

 


Object, Scene Recognition and Segmentation

 

Object of Interest Extraction

Object of Interest Extraction

Automatic Object of Interest Extraction from a Single Image:

 

Context Aware Visual Recognition

SceneParsing

Context Aware Visual Representation:


Shadow and Illumination Modeling

Face

Face Relighting from a Single Image:

Shadow

Detect Outdoor Shadow:



Other Applications

Mobile Video Retargeting:

Mobile HCI

Vision based HCI on Mobile Devices:

CoRobot

Ego-Centric Vision based Co-Robot:

  • Jingzhe Zhang^, Lishuo Zhuang^, Yang Wang^, Yameng Zhou^, Yan Meng, and Gang Hua, "An Egocentric Vision based Assistive Co-robot", in Proc. International Conf. on Rehabilitation Robotics (ICORR'2013), Seattle, WA, June 2013.
  • Jingzhe Zhang^, Lishuo Zhuang^, Yang Wang^, Yameng Zhou^, Yan Meng^, and Gang Hua, ``Video Demo: An Egocentric Vision based Assistive Co-robot,'', in Proc. The 3rd IEEE International Workshop on Mobile Vision in conjunction with CVPR'2013, Portland, OR, June, 2013.

Site Meter